Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution.
arXiv:2607. 13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated process-supervision method based on backward leave-one-turn attribution.
arXiv:2607. 13501v2 Announce Type: replace Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
arXiv:2608. 07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence.
The paper explores how dense, turn-level reward structures can improve reinforcement learning for large language model agents in multi-turn tasks. It introduces three reward granularity types—terminal, delayed, and per-turn—and adapts Group Relative Policy Optimization and Proximal Policy Optimization to each. Experiments on search and game agents show that per-turn rewards consistently yield better training dynamics, faster convergence, and higher answer correctness compared to sparse terminal or delayed rewards.
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
arXiv:2608. 06128v1 Announce Type: new Abstract: Search agents extend large language models beyond static parametric memory by enabling them to acquire and use ex ternal evidence during multi-step reasoning.
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
arXiv:2507.21931v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks....